I got some very spicy ones too, but I wasn’t sure whether that broke the rules.

Midjourney v6 Prompt: a group of large, beautiful barbarian women on an alien planet, The women are dressed in minimalistic titanes made of skins and furs, suggesting a primitive culture. They are encountering Frog and Toad, space explorers from earth for the first time, frog and toad are the size of small humans, The scene is set in an otherworldly landscape with Frog and Toad’s round, retro-futuristic spacecraft in the background, highly detailed, 16:9 aspect ratio, in the style of frank frazetta and Boris Vallejo --v 6.0** - Upscaling (Creative) by <@1015838285202985040> (93%) (fast)

  • Flumpkin@slrpnk.net
    link
    fedilink
    English
    arrow-up
    10
    arrow-down
    2
    ·
    9 months ago

    Wow. I honestly don’t understand how people think these AI models don’t exhibit creativity.

    • CheeseNoodle@lemmy.world
      link
      fedilink
      English
      arrow-up
      12
      ·
      9 months ago

      After much messing around with several models lately. They can put anything together so long as you can find the basic components on google. Its like if you had a magic photoshop filter where you could copy two women and two men onto a desert background, throw some frog heads on the guys, stick a spaceship in there and have it all somehow blend together.

      Where it falls apart is when you ask it to make something that can’t be assembled out of basic and well documented components. It can’t really do animal human hybrids unless they’re that kind or just a person with their limbs randomly turning into whole animals, it also struggles with changes to the fundemental structure of things so a humanoid alien with 4 arms is rarely going to work or even a vehicle with an unusual number of wheels for that vehicle.

      Ultimately AI can remix existing art extremely well but it struggles to create anything it doesn’t already have hundreds of examples of.

      • DominusOfMegadeusOP
        link
        fedilink
        English
        arrow-up
        7
        ·
        edit-2
        9 months ago

        I have tried for many, many hours to recreate a room from a childhood nighmare. None of them can do it because they don’t understand scale, or spatial relationships, or physical positioning though.

      • Flumpkin@slrpnk.net
        link
        fedilink
        English
        arrow-up
        4
        arrow-down
        1
        ·
        9 months ago

        Ok, “exhibit a limited form of creativity” :)

        Maybe you need some different mechanisms / models to allow what you are describing. But I’m sure we’ll get there sooner or later.